In [3]:
pip install matplotlib
In [2]:
pip install altair
In [8]:
pip install folium
In [5]:
import datetime as dt
import matplotlib.pyplot as plt
from matplotlib import style
import pandas as pd
import altair as alt
import folium as folium
In [6]:
ca_covid = pd.read_csv("https://raw.githubusercontent.com/datadesk/california-coronavirus-data/master/latimes-place-totals.csv")
ca_covid.head()
Out[6]:
In [7]:
# Unique County Names
county_name_list = ca_covid['county'].unique()
county_name_list = county_name_list.tolist()
county_name_list.insert(0, 'Select One')
print('Unique County Names: %d' % len(county_name_list))
In [8]:
county_name = 'Orange'
ca_county = ca_covid[ca_covid['county']== county_name]
ca_county = ca_county.sort_values('date', ascending = True)
ca_county.head()
Out[8]:
In [9]:
city_name = 'Irvine'
ca_city = ca_county[ca_county['place']== city_name]
ca_city = ca_city.sort_values('date', ascending = True)
ca_city.head()
Out[9]:
In [10]:
style.use('ggplot')
ax = plt.gca()
df_county.plot(kind='line',x='date',y='confirmed_cases', color='green', ax=ax, figsize=(20,10))
plt.title('Number of Cases In ' + county_name +' County')
plt.xlabel('date')
plt.ylabel('confirmed_cases')
plt.show()
In [6]:
import ipywidgets as widgets
from IPython.display import clear_output
default_county = 'Orange'
country_widget = widgets.Dropdown(
options= county_name_list,
value= default_county,
description='county:',
)
def refresh_chart(county_name):
# reset plot and widget
clear_output(wait=True)
display(country_widget)
if county_name != 'Select One':
ca_counties = pd.read_csv("https://raw.githubusercontent.com/datadesk/california-coronavirus-data/master/latimes-place-totals.csv")
ca_county = ca_counties[ca_counties['county'] == county_name]
ca_county = ca_county.sort_values('date', ascending = True)
style.use('ggplot')
ax = plt.gca()
ca_county.plot(kind='line',x='date',y='confirmed_cases', color='green', ax=ax, figsize=(20,10))
plt.title('Number of Cases In ' + county_name +' County')
plt.xlabel('date')
plt.ylabel('confirmed_cases')
plt.show()
def on_change(change):
if change['type'] == 'change' and change['name'] == 'value':
refresh_chart(change['new'])
country_widget.observe(on_change)
display(country_widget)
refresh_chart(default_county)
In [11]:
ca_covid.head()
Out[11]:
In [12]:
ca_latest_county = ca_covid[ca_covid['date'] == ca_covid['date'].max()]
del ca_latest_county['date']
del ca_latest_county['confirmed_cases']
ca_latest_county.head()
Out[12]:
In [13]:
ca_county.query("confirmed_cases == 'NaN'")
Out[13]:
In [14]:
ca_county.query("x == 'NaN'")
Out[14]:
In [15]:
ca_county.query("y == 'NaN'")
Out[15]:
In [16]:
ca_covid.query("x > 0")
Out[16]:
In [17]:
ca_county.query("date.isnull()", engine='python')
Out[17]:
In [18]:
ca_county = ca_county.query("confirmed_cases != 'NaN' & x < 0 & x != 'NaN' & date.notnull()", engine='python')
ca_county.head()
Out[18]:
In [19]:
ca_covid = ca_covid.query("confirmed_cases != 'NaN' & x < 0 & x != 'NaN' & date.notnull()", engine='python')
ca_covid.head()
Out[19]:
In [20]:
ca_city = ca_city.query("confirmed_cases != 'NaN' & x < 0 & x != 'NaN' & date.notnull()", engine='python')
ca_city.head()
Out[20]:
In [41]:
import requests as r
import json
from IPython.display import HTML
ca_json = r.get('https://raw.githubusercontent.com/OpenDataDE/State-zip-code-GeoJSON/master/ca_california_zip_codes_geo.min.json')
print(ca_json)
cali_map = folium.Map(location=[33.669445,-117.823059], zoom_start=12)
folium.Choropleth(geo_data=ca_json.json()['features'][512],
fill_color='red',
fill_opacity=0.5,
line_opacity=0.8,
key_on='feature.properties.ZCTA5CE10').add_to(cali_map)
cali_map.save('plot_data_2.html')
HTML('<iframe src=plot_data_2.html width=800 height=500></iframe>')
Out[41]:
In [21]:
ca_city.head()
Out[21]:
In [22]:
ca_city.shape
Out[22]:
In [23]:
ca_city = ca_city.sort_values(by=["date"], ascending=True)
ca_city.tail()
Out[23]:
In [24]:
ca_city.iloc[0]['date']
Out[24]:
In [25]:
lastdate = ca_city.iloc[-1]['date']
lastdate
Out[25]:
In [30]:
irvine_single_day = ca_city.query('date==@lastdate')
irvine_single_day = irvine_single_day.sort_values(by=["confirmed_cases"], ascending=True)
irvine_single_day
Out[30]:
In [27]:
orange_single_day = ca_county.query('date==@lastdate')
orange_single_day = orange_single_day.sort_values(by=["confirmed_cases"], ascending=True)
orange_single_day.head()
Out[27]:
In [31]:
ca_single_day = ca_covid.query('date==@lastdate')
ca_single_day
Out[31]:
In [32]:
ca_single_day = ca_single_day.query("confirmed_cases != 'NaN' & x < 0 & x != 'NaN' & date.notnull()", engine='python')
ca_single_day.head()
Out[32]:
In [33]:
ca_city = ca_city.query("place=='Irvine'")
ca_city
Out[33]:
In [34]:
ca_covid.confirmed_cases.describe()
Out[34]:
In [35]:
ca_covid.groupby("county").confirmed_cases.describe()
Out[35]:
In [36]:
ca_covid.groupby("county").confirmed_cases.describe().sort_values(by=["max"], ascending=False)
Out[36]:
In [35]:
ca_county.groupby("place").confirmed_cases.describe().sort_values(by=["max"], ascending=False).head(50)
Out[35]:
In [37]:
!pip install plotly
In [38]:
import plotly.express as px
Irvine = ca_covid.query("place == ['Irvine']")
px.bar(Irvine,
x='date',
y='confirmed_cases')
In [39]:
OC_Cities = ca_county.query("place == ['Santa Ana','Anaheim','Irvine']")
px.bar(OC_Cities,
x='date',
y='confirmed_cases',
color = 'place')
In [40]:
px.scatter(orange_single_day,
x='x',
y='y',
hover_name='place',
color='confirmed_cases')
In [41]:
px.scatter(ca_single_day,
x='x',
y='y',
hover_name='place',
color='confirmed_cases')
In [42]:
px.scatter(ca_single_day,
x='x',
y='y',
color='confirmed_cases',
size='confirmed_cases',
size_max=40,
hover_name='place',
title = 'Confirmed Cases for ' + lastdate)
In [43]:
px.scatter(ca_single_day,
x='x',
y='y',
color='confirmed_cases',
size='confirmed_cases',
size_max=40,
hover_name='place',
color_continuous_scale = 'RdYlGn_r') # added _r to reverse color scheme
In [44]:
ca_single_day_mean = ca_single_day.confirmed_cases.mean()
ca_single_day_mean
Out[44]:
In [45]:
px.scatter(ca_single_day,
x='x',
y='y',
color='confirmed_cases',
size='confirmed_cases',
size_max=40,
hover_name='place',
color_continuous_scale = 'RdYlGn_r', # added _r to reverse color scheme
range_color = (0,ca_single_day_mean * 2) # double the mean
)
In [46]:
orange_mean = ca_county.confirmed_cases.mean()
orange_mean
Out[46]:
In [47]:
px.scatter(ca_county,
x='x',
y='y',
color='confirmed_cases',
size='confirmed_cases',
size_max=40,
hover_name='place',
animation_frame='date', # this creates a frame by frame animation by day
color_continuous_scale = 'RdYlGn_r',
range_color = (0,orange_mean*2))
In [48]:
fig = px.scatter_geo(ca_single_day,
lon='x',
lat='y',
color='confirmed_cases',
size='confirmed_cases',
size_max=40,
hover_name='place',
scope='usa',
color_continuous_scale = 'RdYlGn_r',
range_color = (0,ca_single_day_mean * 2) # double the mean
)
fig.update_geos(fitbounds="locations")
In [49]:
fig = px.scatter_geo(ca_county,
lon='x',
lat='y',
color='confirmed_cases',
size='confirmed_cases',
size_max=40,
hover_name='place',
scope='usa',
animation_frame='date',
color_continuous_scale = 'RdYlGn_r',
range_color = (0,orange_mean*2))
fig.update_geos(fitbounds="locations")
In [71]:
# Set the map up
map_orange = folium.Map(location=[33.6846, -117.8265],
tiles = "Stamen Toner",
zoom_start = 9)
# Simple marker
folium.Marker([33.6846, -117.8265],
popup='Irvine',
icon=folium.Icon(color='green')
).add_to(map_orange)
# Circle marker
folium.CircleMarker([33.6846, -117.8265],
radius=30,
popup='Irvine',
color='red',
).add_to(map_orange)
# Interactive marker
map_orange.add_child(folium.ClickForMarker(popup="Irvine"))
map_orange
Out[71]:
In [50]:
locations = ca_county[['x', 'y']]
locationlist = locations.values.tolist()
len(locationlist)
locationlist[7]
Out[50]:
In [51]:
# Create a Map instance
map = folium.Map(location=[34,-118],
zoom_start=8,
control_scale=True
)
map
Out[51]:
In [52]:
# Create a Map instance with different basemap
map = folium.Map(location=[34,-118],
zoom_start=8,
control_scale=True,
tiles='CartoDB dark_matter',
attr= '© <a href="https://www.openstreetmap.org/copyright">OpenStreetMap</a> contributors © <a href="https://carto.com/attributions">CARTO</a>')
map
Out[52]:
In [53]:
# add a circle
my_circle = folium.Circle(
radius=10000, # this is in meters
location=[34,-118],
color='crimson',
fill=True,
)
my_circle.add_to(map)
map
Out[53]:
In [54]:
orange_single_day.plot(x ='x', y='y', kind = 'scatter')
Out[54]:
In [55]:
orange_single_day = orange_single_day.query("confirmed_cases != 'NaN' & x < 0 & x != 'NaN' & date.notnull()", engine='python')
orange_single_day.head()
Out[55]:
In [99]:
# loop through the rows in Los Angeles, and create a circle based on confirmed cases
for index, row in orange_single_day.iterrows():
# set up the variables
lat = row['y']
lon = row['x']
label = str(row['confirmed_cases']) + ' confirmed cases in ' + row['place']
size = row['confirmed_cases']
# create a circle for every row
circle = folium.Circle(
radius=size,
location=[lat,lon],
tooltip = label,
color='crimson',
fill = True
)
circle.add_to(map)
# show the map
map
Out[99]:
In [56]:
import altair as alt
In [57]:
# reset the map (only way to get rid of circles)
map = folium.Map(location=[34,-118],
zoom_start=8,
control_scale=True,
tiles='CartoDB dark_matter',
attr= '© <a href="https://www.openstreetmap.org/copyright">OpenStreetMap</a> contributors © <a href="https://carto.com/attributions">CARTO</a>')
In [58]:
# create a function to create circles, and also add a chart in the popup window (a lot here, will break it up later)
def createCircle(lat,lon,size,place,label):
# create a bar chart for each circle
bar = alt.Chart(ca_county.query('place == @place')).mark_bar().encode(
x=alt.X('date', axis=alt.Axis(labels=False)), # turn the labels off because there are too many
y='confirmed_cases',
color='confirmed_cases',
tooltip = ['date','place','confirmed_cases']
).properties(width=400,height=200)
# add the bar chart as a folium feature
vega = folium.features.VegaLite(
bar,
width=600,
height=200,
)
# create the circle
circle = folium.Circle(
radius=size,
location=[lat,lon],
tooltip = label,
color='crimson',
fill = True
)
# create a popup
popup = folium.Popup()
# add the chart to the popup
vega.add_to(popup)
# add the popup to the circle
popup.add_to(circle)
# add the circle to the map
circle.add_to(map)
In [59]:
# loop through the rows in Los Angeles, and create a circle based on confirmed cases
for index, row in orange_single_day.iterrows():
label = str(row['confirmed_cases']) + ' confirmed cases in ' + row['place']
createCircle(row['y'],row['x'],row['confirmed_cases'],row['place'],label)
In [60]:
# show the map
map
Out[60]:
In [61]:
# save it!
map.save('index.html')
In [62]:
orange_single_day.head()
Out[62]:
In [63]:
orange_single_day.tail()
Out[63]:
In [64]:
style.use('ggplot')
ax = plt.gca()
orange_single_day.plot(kind='line',x='place',y='confirmed_cases', color='green', ax=ax, figsize=(20,10))
plt.title('Confirmed Cases in Orange County')
plt.xlabel('Place')
plt.ylabel('Count')
plt.show()
In [66]:
ca_county = ca_county.query("confirmed_cases != 'NaN' & x < 0 & x != 'NaN' & date.notnull()", engine='python')
ca_county.head()
Out[66]:
In [154]:
In [ ]: